On Fri, 2010-08-13 at 12:45 -0700, Suresh Siddha wrote:
quoted text
> plain text document attachment (move_sched_avg_update.patch)
> Currently sched_avg_update() (which updates rt_avg stats in the rq) is getting
> called from scale_rt_power() (in the load balance context) which doesn't take
> rq->lock.

Right, but I think it doesn't need to, as its never accessed cross CPU
(except maybe for /proc/sched_debug, and who cares about that).

The (other) odd case is NO_HZ idle balancing, but there the actual CPU
won't be updating the fields, so the remote CPU doing NO_HZ idle
balancing should be good to touch it.

quoted text
> Fix it by moving the sched_avg_update() to more appropriate update_cpu_load()
> where the CFS load gets updated aswell.

Right, except it breaks things a bit, at the very least you really need
that update right before reading it, otherwise you can end up with >100%
fractions, which are odd indeed ;-)


--
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/